[release-v1.34] Unify config files for ccm and csi (#483)

* Unify config files for ccm and csi

* switch back to separate configs for ccm and csi

* align GetConfig methods and cleanup

* add migration documentation

* fix lb migration

---------

Co-authored-by: Robert Kaussow <mail@thegeeklab.de>

Author: stackit-ske

cmd/cloud-controller-manager/main.go

@@ -36,7 +36,7 @@ var (
 func main() {
 	ccmOptions, err := options.NewCloudControllerManagerOptions()
 	if err != nil {
-		klog.Fatalf("unable to initialize command options: %v", err)
+		klog.Fatalf("Unable to initialize command options: %v", err)
 	}
 
 	fmt.Println("starting Controller")
@@ -91,7 +91,7 @@ func cloudInitializer(ctx context.Context) func(config *cloudcontrollerconfig.Co
 
 		if !cloud.HasClusterID() {
 			if config.ComponentConfig.KubeCloudShared.AllowUntaggedCloud {
-				klog.Warning("detected a cluster without a ClusterID. A ClusterID will be required in the future. Please tag your cluster to avoid any future issues")
+				klog.Warning("Detected a cluster without a ClusterID. A ClusterID will be required in the future. Please tag your cluster to avoid any future issues")
 			} else {
 				klog.Fatalf(
 					"no ClusterID found. A ClusterID is required for the cloud provider to function properly. " +

deploy/csi-plugin/controllerplugin.yaml

@@ -105,7 +105,7 @@ spec:
         - name: CSI_ENDPOINT
           value: unix://csi/csi.sock
         - name: CLOUD_CONFIG
-          value: /etc/config/cloud.conf
+          value: /etc/config/cloud.yaml
         - name: CLUSTER_NAME
           value: kubernetes
         - name: STACKIT_SERVICE_ACCOUNT_KEY_PATH

deploy/csi-plugin/nodeplugin.yaml

@@ -64,7 +64,7 @@ spec:
         - name: CSI_ENDPOINT
           value: unix://csi/csi.sock
         - name: CLOUD_CONFIG
-          value: /etc/config/cloud.conf
+          value: /etc/config/cloud.yaml
         imagePullPolicy: "IfNotPresent"
         ports:
         - containerPort: 9808

docs/migration/configuration.md

@@ -0,0 +1,96 @@
+# Migration Guide: CCM and CSI Configuration to Unified YAML Format
+
+## Introduction
+
+This guide provides step-by-step instructions for migrating from the legacy Cloud Controller Manager (CCM) and Container Storage Interface (CSI) configurations to the new unified YAML-based configuration format.
+
+## Overview
+
+The migration involves:
+
+- Updating CCM and CSI configurations to use the new unified YAML format
+- Mapping legacy configuration keys to new schema
+- Ensuring compatibility with the latest version of the STACKIT Kubernetes integration
+
+**Note**: While the new format uses a unified structure, CCM and CSI configurations remain in separate files but follow the same YAML schema.
+
+## Removed Configuration Options
+
+The following configuration options have been removed in the new format:
+
+### CCM
+
+- `nonStackitClassNames` - No longer supported
+
+### CSI
+
+- `node-volume-attach-limit` - No longer configurable
+
+## Old Configuration Reference
+
+### CCM Configuration
+
+```yaml
+# cloudprovider.yaml
+projectId: my-stackit-project-id
+networkId: my-stackit-network-id
+region: eu01
+nonStackitClassNames: my-non-stackit-class
+extraLabels:
+  key1: value1
+  key2: value2
+metadata:
+  searchOrder: "configDrive,metadataService"
+  requestTimeout: "5s"
+loadBalancerApi:
+  url: https://loadbalancer.example.com
+```
+
+### CSI Configuration
+
+```ini
+# cloudprovider.conf
+[Global]
+project-id = "my-stackit-project-id"
+iaas-api-url = "https://iaas.example.com"
+[Metadata]
+search-order = "configDrive,metadataService"
+request-timeout = "5s"
+[BlockStorage]
+node-volume-attach-limit = 20
+rescan-on-resize = true
+```
+
+## New Configuration Reference
+
+### CCM Configuration
+
+```yaml
+# cloudprovider.yaml
+global:
+  projectId: my-stackit-project-id
+  region: eu01
+metadata:
+  searchOrder: "configDrive,metadataService"
+  requestTimeout: "5s"
+loadBalancer:
+  api: https://loadbalancer.example.com
+  networkId: my-stackit-network-id
+  extraLabels:
+    key1: value1
+    key2: value2
+```
+
+### CSI Configuration
+
+```yaml
+# cloudprovider.conf
+global:
+  projectId: my-stackit-project-id
+  iaasApi: https://iaas.example.com
+metadata:
+  searchOrder: "configDrive,metadataService"
+  requestTimeout: "5s"
+blockStorage:
+  rescanOnResize: true
+```

go.mod

@@ -19,11 +19,11 @@ require (
 	github.com/stackitcloud/stackit-sdk-go/services/iaas v1.3.0
 	github.com/stackitcloud/stackit-sdk-go/services/loadbalancer v1.7.0
 	go.uber.org/mock v0.6.0
+	go.yaml.in/yaml/v2 v2.4.3
 	golang.org/x/sync v0.19.0
 	golang.org/x/sys v0.40.0
 	google.golang.org/grpc v1.78.0
 	google.golang.org/protobuf v1.36.11
-	gopkg.in/gcfg.v1 v1.2.3
 	gopkg.in/yaml.v3 v3.0.1
 	k8s.io/api v0.34.3
 	k8s.io/apimachinery v0.34.3
@@ -114,7 +114,6 @@ require (
 	go.opentelemetry.io/proto/otlp v1.5.0 // indirect
 	go.uber.org/multierr v1.11.0 // indirect
 	go.uber.org/zap v1.27.0 // indirect
-	go.yaml.in/yaml/v2 v2.4.3 // indirect
 	go.yaml.in/yaml/v3 v3.0.4 // indirect
 	golang.org/x/crypto v0.44.0 // indirect
 	golang.org/x/exp v0.0.0-20250620022241-b7579e27df2b // indirect
@@ -130,7 +129,6 @@ require (
 	gopkg.in/evanphx/json-patch.v4 v4.12.0 // indirect
 	gopkg.in/inf.v0 v0.9.1 // indirect
 	gopkg.in/natefinch/lumberjack.v2 v2.2.1 // indirect
-	gopkg.in/warnings.v0 v0.1.2 // indirect
 	gopkg.in/yaml.v2 v2.4.0 // indirect
 	k8s.io/apiserver v0.34.2 // indirect
 	k8s.io/component-helpers v0.34.2 // indirect

go.sum

@@ -345,14 +345,10 @@ gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntN
 gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=
 gopkg.in/evanphx/json-patch.v4 v4.12.0 h1:n6jtcsulIzXPJaxegRbvFNNrZDjbij7ny3gmSPG+6V4=
 gopkg.in/evanphx/json-patch.v4 v4.12.0/go.mod h1:p8EYWUEYMpynmqDbY58zCKCFZw8pRWMG4EsWvDvM72M=
-gopkg.in/gcfg.v1 v1.2.3 h1:m8OOJ4ccYHnx2f4gQwpno8nAX5OGOh7RLaaz0pj3Ogs=
-gopkg.in/gcfg.v1 v1.2.3/go.mod h1:yesOnuUOFQAhST5vPY4nbZsb/huCgGGXlipJsBn0b3o=
 gopkg.in/inf.v0 v0.9.1 h1:73M5CoZyi3ZLMOyDlQh031Cx6N9NDJ2Vvfl76EDAgDc=
 gopkg.in/inf.v0 v0.9.1/go.mod h1:cWUDdTG/fYaXco+Dcufb5Vnc6Gp2YChqWtbxRZE0mXw=
 gopkg.in/natefinch/lumberjack.v2 v2.2.1 h1:bBRl1b0OH9s/DuPhuXpNl+VtCaJXFZ5/uEFST95x9zc=
 gopkg.in/natefinch/lumberjack.v2 v2.2.1/go.mod h1:YD8tP3GAjkrDg1eZH7EGmyESg/lsYskCTPBJVb9jqSc=
-gopkg.in/warnings.v0 v0.1.2 h1:wFXVbFY8DY5/xOe1ECiWdKCzZlxgshcYVNkBHstARME=
-gopkg.in/warnings.v0 v0.1.2/go.mod h1:jksf8JmL6Qr/oQM2OXTHunEvvTAsrWBLb6OOjuVWRNI=
 gopkg.in/yaml.v2 v2.4.0 h1:D8xgwECY7CYvx+Y2n4sBz93Jn9JRvxdiyyo8CTfuKaY=
 gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ=
 gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

pkg/ccm/instances.go

@@ -65,7 +65,7 @@ func NewInstance(client stackit.NodeClient, projectID, region string) (*Instance
 func (i *Instances) InstanceExists(ctx context.Context, node *corev1.Node) (bool, error) {
 	_, err := i.getInstance(ctx, node)
 	if errors.Is(err, cloudprovider.InstanceNotFound) {
-		klog.V(6).Infof("instance not found for node: %s", node.Name)
+		klog.V(6).Infof("Instance not found for node: %s", node.Name)
 		return false, nil
 	}
 	if err != nil {
@@ -94,7 +94,7 @@ func (i *Instances) InstanceShutdown(ctx context.Context, node *corev1.Node) (bo
 func (i *Instances) InstanceMetadata(ctx context.Context, node *corev1.Node) (*cloudprovider.InstanceMetadata, error) {
 	server, err := i.getInstance(ctx, node)
 	if errors.Is(err, cloudprovider.InstanceNotFound) {
-		klog.V(6).Infof("instance not found for node: %s", node.Name)
+		klog.V(6).Infof("Instance not found for node: %s", node.Name)
 		return nil, nil
 	}
 	if err != nil {

pkg/ccm/loadbalancer.go

@@ -39,25 +39,29 @@ type MetricsRemoteWrite struct {
 
 // LoadBalancer is used for creating and maintaining load balancers.
 type LoadBalancer struct {
-	client      stackit.LoadbalancerClient
-	recorder    record.EventRecorder // set in CloudControllerManager.Initialize
-	projectID   string
-	networkID   string
-	extraLabels map[string]string
+	client    stackit.LoadbalancerClient
+	recorder  record.EventRecorder // set in CloudControllerManager.Initialize
+	projectID string
+	opts      LoadBalancerOpts
 	// metricsRemoteWrite setting this enables remote writing of metrics and nil means it is disabled
 	metricsRemoteWrite *MetricsRemoteWrite
 }
 
+type LoadBalancerOpts struct {
+	API         string            `yaml:"api"`
+	NetworkID   string            `yaml:"networkId"`
+	ExtraLabels map[string]string `yaml:"extraLabels"`
+}
+
 var _ cloudprovider.LoadBalancer = (*LoadBalancer)(nil)
 
-func NewLoadBalancer(client stackit.LoadbalancerClient, projectID, networkID string, extraLabels map[string]string, metricsRemoteWrite *MetricsRemoteWrite) (*LoadBalancer, error) { //nolint:lll // looks weird when shortened
+func NewLoadBalancer(client stackit.LoadbalancerClient, projectID string, opts LoadBalancerOpts, metricsRemoteWrite *MetricsRemoteWrite) (*LoadBalancer, error) { //nolint:lll // looks weird when shortened
 	// LoadBalancer.recorder is set in CloudControllerManager.Initialize
 	return &LoadBalancer{
 		client:             client,
 		projectID:          projectID,
-		networkID:          networkID,
+		opts:               opts,
 		metricsRemoteWrite: metricsRemoteWrite,
-		extraLabels:        extraLabels,
 	}, nil
 }
 
@@ -126,7 +130,7 @@ func (l *LoadBalancer) EnsureLoadBalancer( //nolint:gocyclo // not really comple
 		return nil, fmt.Errorf("reconcile metricsRemoteWrite: %w", err)
 	}
 
-	spec, events, err := lbSpecFromService(service, nodes, l.networkID, l.extraLabels, observabilityOptions)
+	spec, events, err := lbSpecFromService(service, nodes, l.opts, observabilityOptions)
 	if err != nil {
 		return nil, fmt.Errorf("invalid load balancer specification: %w", err)
 	}
@@ -206,12 +210,12 @@ func (l *LoadBalancer) createLoadBalancer(ctx context.Context, clusterName strin
 		return nil, fmt.Errorf("reconcile metricsRemoteWrite: %w", err)
 	}
 
-	spec, events, err := lbSpecFromService(service, nodes, l.networkID, l.extraLabels, metricsRemoteWrite)
+	spec, events, err := lbSpecFromService(service, nodes, l.opts, metricsRemoteWrite)
 	if err != nil {
 		return nil, fmt.Errorf("invalid load balancer specification: %w", err)
 	}
-	if l.extraLabels != nil {
-		spec.Labels = ptr.To(l.extraLabels)
+	if l.opts.ExtraLabels != nil {
+		spec.Labels = ptr.To(l.opts.ExtraLabels)
 	}
 	for _, event := range events {
 		l.recorder.Event(service, event.Type, event.Reason, event.Message)
@@ -238,7 +242,7 @@ func (l *LoadBalancer) createLoadBalancer(ctx context.Context, clusterName strin
 // It is not called on controller start-up. EnsureLoadBalancer must also ensure to update targets.
 func (l *LoadBalancer) UpdateLoadBalancer(ctx context.Context, clusterName string, service *corev1.Service, nodes []*corev1.Node) error {
 	// only TargetPools are used from spec
-	spec, events, err := lbSpecFromService(service, nodes, l.networkID, l.extraLabels, nil)
+	spec, events, err := lbSpecFromService(service, nodes, l.opts, nil)
 	if err != nil {
 		return fmt.Errorf("invalid service: %w", err)
 	}

pkg/ccm/loadbalancer_spec.go

@@ -244,16 +244,15 @@ func getPlanID(service *corev1.Service) (planID *string, msgs []string, err erro
 func lbSpecFromService( //nolint:funlen,gocyclo // It is long but not complex.
 	service *corev1.Service,
 	nodes []*corev1.Node,
-	networkID string,
-	extraLabels map[string]string,
+	opts LoadBalancerOpts,
 	observability *loadbalancer.LoadbalancerOptionObservability,
 ) (*loadbalancer.CreateLoadBalancerPayload, []Event, error) {
 	lb := &loadbalancer.CreateLoadBalancerPayload{
 		Options: &loadbalancer.LoadBalancerOptions{},
 		Networks: &[]loadbalancer.Network{
 			{
 				Role:      utils.Ptr(loadbalancer.NETWORKROLE_LISTENERS_AND_TARGETS),
-				NetworkId: &networkID,
+				NetworkId: &opts.NetworkID,
 			},
 		},
 	}
@@ -262,7 +261,7 @@ func lbSpecFromService( //nolint:funlen,gocyclo // It is long but not complex.
 		lb.Networks = &[]loadbalancer.Network{
 			{
 				Role:      utils.Ptr(loadbalancer.NETWORKROLE_TARGETS),
-				NetworkId: &networkID,
+				NetworkId: &opts.NetworkID,
 			}, {
 				Role:      utils.Ptr(loadbalancer.NETWORKROLE_LISTENERS),
 				NetworkId: &listenerNetwork,
@@ -272,14 +271,14 @@ func lbSpecFromService( //nolint:funlen,gocyclo // It is long but not complex.
 		lb.Networks = &[]loadbalancer.Network{
 			{
 				Role:      utils.Ptr(loadbalancer.NETWORKROLE_LISTENERS_AND_TARGETS),
-				NetworkId: &networkID,
+				NetworkId: &opts.NetworkID,
 			},
 		}
 	}
 
 	// Add extraLabels if set
-	if extraLabels != nil {
-		lb.Labels = ptr.To(extraLabels)
+	if opts.ExtraLabels != nil {
+		lb.Labels = ptr.To(opts.ExtraLabels)
 	}
 
 	// Add metric metricsRemoteWrite settings